Your recordings stay
on your machine.

Ibis watches a folder on your computer and transcribes every audio file automatically, using a local Whisper model that runs entirely offline. Drop a voice memo. Get a text file. Nothing ever leaves your computer.

Cloud transcription services receive your recordings, process them on remote servers, and store them under terms of service you agreed to but probably did not read. The convenience is real. So is the trade. For people whose audio is sensitive by profession or by preference, the trade has never been acceptable. The local alternatives, until recently, were either bad or inaccessible.

Ibis is the alternative. It uses OpenAI’s Whisper models; the speech model downloads once at first launch and is verified by checksum. It runs on the CPU of an ordinary machine. No GPU required. No account. No internet after that one-time download. The audio never moves.

Point Ibis at a watch folder you choose. Every audio file you drop in becomes a transcript, automatically, while you do other things.

The setup is three steps. Point Ibis at a folder in Settings. Drop in any MP3, WAV, or M4A file. A transcript appears next to the recording, timestamped and named to match. A notification confirms the job is done. The original recording stays where you put it.

That is the entire interaction model. There is no batch to run and no queue to manage. The tool is invisible until it is useful.

The privacy claim is structural, not aspirational. The Whisper model lives on your disk after a one-time, checksum-verified download. The watch-folder process runs locally. The transcripts are written to your disk. Recordings and transcripts can be encrypted at rest using age with X25519 keys, and originals are kept unless you explicitly choose secure removal. The secret key lives in the Windows Credential Manager or macOS Keychain, not in any file Ibis can read. We do not see it. We do not sync it.

Whisper’s models cover all 99 languages it supports, and there is nothing to download per language. Once your chosen model is on disk, the whole multilingual capability is available offline.

On the standard public ASR benchmark, our published Ibis v1.0 evaluation measured 1.94% word-error rate on LibriSpeech test-clean and 3.87% on test-other (harder audio with accents and noise), using Whisper large-v3-turbo with int8 quantization. Both numbers are within 0.27 percentage points of OpenAI’s published full-precision baselines.

A note on speed. Ibis runs on CPU, so expect roughly real-time transcription on consumer hardware; on Apple silicon the engine accelerates via Metal. The rebuilt engine is being re-benchmarked before launch, and accuracy figures will be republished with it.

Methodology, per-split breakdown, and full reproducibility commands are in the substantiation paper at doi.org/10.5281/zenodo.19931717.

Ibis was built for the people who keep encountering the same problem. Journalists protect sources and need transcripts of interviews that should not pass through a third-party server. Therapists and clinicians handle session recordings under HIPAA constraints; Ibis processes locally and is built with the intention to support adherence to those rules. Attorneys work with privileged communications and depositions. Researchers bound by IRB protocols often cannot use cloud services for participant data. Knowledge workers want voice notes flowing into their second brains automatically. Podcasters and creators need transcripts for show notes and captions in seconds, offline.

The tool does not care which of these you are. The transcript appears, locally, with a timestamp and a filename. The audio stays where it was.

Ibis ships in three flavors. Personal is the launch tier: $24, one-time, up to three devices, lifetime updates for v1.x. Pro is on the Q4 2026 roadmap at $59 with project workspaces and priority support; the Pro waitlist is open below. Team is a published multi-seat bundle for practices and firms: 5 seats at $99 (Personal) or $249 (Pro); 10 seats at $179 (Personal) or $449 (Pro). Questions about larger deployments go to ibis@simdadllc.com.